summaryrefslogtreecommitdiff
path: root/drivers/mtd/mtdpstore.c
blob: a4fe6060b960f7c83539d15e3429ccaffff13195 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
// SPDX-License-Identifier: GPL-2.0

#define dev_fmt(fmt) "mtdoops-pstore: " fmt

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/pstore_blk.h>
#include <linux/mtd/mtd.h>
#include <linux/bitops.h>

static struct mtdpstore_context {
	int index;
	struct pstore_blk_config info;
	struct pstore_device_info dev;
	struct mtd_info *mtd;
	unsigned long *rmmap;		/* removed bit map */
	unsigned long *usedmap;		/* used bit map */
	/*
	 * used for panic write
	 * As there are no block_isbad for panic case, we should keep this
	 * status before panic to ensure panic_write not failed.
	 */
	unsigned long *badmap;		/* bad block bit map */
} oops_cxt;

static int mtdpstore_block_isbad(struct mtdpstore_context *cxt, loff_t off)
{
	int ret;
	struct mtd_info *mtd = cxt->mtd;
	u64 blknum;

	off = ALIGN_DOWN(off, mtd->erasesize);
	blknum = div_u64(off, mtd->erasesize);

	if (test_bit(blknum, cxt->badmap))
		return true;
	ret = mtd_block_isbad(mtd, off);
	if (ret < 0) {
		dev_err(&mtd->dev, "mtd_block_isbad failed, aborting\n");
		return ret;
	} else if (ret > 0) {
		set_bit(blknum, cxt->badmap);
		return true;
	}
	return false;
}

static inline int mtdpstore_panic_block_isbad(struct mtdpstore_context *cxt,
		loff_t off)
{
	struct mtd_info *mtd = cxt->mtd;
	u64 blknum;

	off = ALIGN_DOWN(off, mtd->erasesize);
	blknum = div_u64(off, mtd->erasesize);
	return test_bit(blknum, cxt->badmap);
}

static inline void mtdpstore_mark_used(struct mtdpstore_context *cxt,
		loff_t off)
{
	struct mtd_info *mtd = cxt->mtd;
	u64 zonenum = div_u64(off, cxt->info.kmsg_size);

	dev_dbg(&mtd->dev, "mark zone %llu used\n", zonenum);
	set_bit(zonenum, cxt->usedmap);
}

static inline void mtdpstore_mark_unused(struct mtdpstore_context *cxt,
		loff_t off)
{
	struct mtd_info *mtd = cxt->mtd;
	u64 zonenum = div_u64(off, cxt->info.kmsg_size);

	dev_dbg(&mtd->dev, "mark zone %llu unused\n", zonenum);
	clear_bit(zonenum, cxt->usedmap);
}

static inline void mtdpstore_block_mark_unused(struct mtdpstore_context *cxt,
		loff_t off)
{
	struct mtd_info *mtd = cxt->mtd;
	u32 zonecnt = mtd->erasesize / cxt->info.kmsg_size;
	u64 zonenum;

	off = ALIGN_DOWN(off, mtd->erasesize);
	zonenum = div_u64(off, cxt->info.kmsg_size);
	while (zonecnt > 0) {
		dev_dbg(&mtd->dev, "mark zone %llu unused\n", zonenum);
		clear_bit(zonenum, cxt->usedmap);
		zonenum++;
		zonecnt--;
	}
}

static inline int mtdpstore_is_used(struct mtdpstore_context *cxt, loff_t off)
{
	u64 zonenum = div_u64(off, cxt->info.kmsg_size);
	u64 blknum = div_u64(off, cxt->mtd->erasesize);

	if (test_bit(blknum, cxt->badmap))
		return true;
	return test_bit(zonenum, cxt->usedmap);
}

static int mtdpstore_block_is_used(struct mtdpstore_context *cxt,
		loff_t off)
{
	struct mtd_info *mtd = cxt->mtd;
	u32 zonecnt = mtd->erasesize / cxt->info.kmsg_size;
	u64 zonenum;

	off = ALIGN_DOWN(off, mtd->erasesize);
	zonenum = div_u64(off, cxt->info.kmsg_size);
	while (zonecnt > 0) {
		if (test_bit(zonenum, cxt->usedmap))
			return true;
		zonenum++;
		zonecnt--;
	}
	return false;
}

static int mtdpstore_is_empty(struct mtdpstore_context *cxt, char *buf,
		size_t size)
{
	struct mtd_info *mtd = cxt->mtd;
	size_t sz;
	int i;

	sz = min_t(uint32_t, size, mtd->writesize / 4);
	for (i = 0; i < sz; i++) {
		if (buf[i] != (char)0xFF)
			return false;
	}
	return true;
}

static void mtdpstore_mark_removed(struct mtdpstore_context *cxt, loff_t off)
{
	struct mtd_info *mtd = cxt->mtd;
	u64 zonenum = div_u64(off, cxt->info.kmsg_size);

	dev_dbg(&mtd->dev, "mark zone %llu removed\n", zonenum);
	set_bit(zonenum, cxt->rmmap);
}

static void mtdpstore_block_clear_removed(struct mtdpstore_context *cxt,
		loff_t off)
{
	struct mtd_info *mtd = cxt->mtd;
	u32 zonecnt = mtd->erasesize / cxt->info.kmsg_size;
	u64 zonenum;

	off = ALIGN_DOWN(off, mtd->erasesize);
	zonenum = div_u64(off, cxt->info.kmsg_size);
	while (zonecnt > 0) {
		clear_bit(zonenum, cxt->rmmap);
		zonenum++;
		zonecnt--;
	}
}

static int mtdpstore_block_is_removed(struct mtdpstore_context *cxt,
		loff_t off)
{
	struct mtd_info *mtd = cxt->mtd;
	u32 zonecnt = mtd->erasesize / cxt->info.kmsg_size;
	u64 zonenum;

	off = ALIGN_DOWN(off, mtd->erasesize);
	zonenum = div_u64(off, cxt->info.kmsg_size);
	while (zonecnt > 0) {
		if (test_bit(zonenum, cxt->rmmap))
			return true;
		zonenum++;
		zonecnt--;
	}
	return false;
}

static int mtdpstore_erase_do(struct mtdpstore_context *cxt, loff_t off)
{
	struct mtd_info *mtd = cxt->mtd;
	struct erase_info erase;
	int ret;

	off = ALIGN_DOWN(off, cxt->mtd->erasesize);
	dev_dbg(&mtd->dev, "try to erase off 0x%llx\n", off);
	erase.len = cxt->mtd->erasesize;
	erase.addr = off;
	ret = mtd_erase(cxt->mtd, &erase);
	if (!ret)
		mtdpstore_block_clear_removed(cxt, off);
	else
		dev_err(&mtd->dev, "erase of region [0x%llx, 0x%llx] on \"%s\" failed\n",
		       (unsigned long long)erase.addr,
		       (unsigned long long)erase.len, cxt->info.device);
	return ret;
}

/*
 * called while removing file
 *
 * Avoiding over erasing, do erase block only when the whole block is unused.
 * If the block contains valid log, do erase lazily on flush_removed() when
 * unregister.
 */
static ssize_t mtdpstore_erase(size_t size, loff_t off)
{
	struct mtdpstore_context *cxt = &oops_cxt;

	if (mtdpstore_block_isbad(cxt, off))
		return -EIO;

	mtdpstore_mark_unused(cxt, off);

	/* If the block still has valid data, mtdpstore do erase lazily */
	if (likely(mtdpstore_block_is_used(cxt, off))) {
		mtdpstore_mark_removed(cxt, off);
		return 0;
	}

	/* all zones are unused, erase it */
	return mtdpstore_erase_do(cxt, off);
}

/*
 * What is security for mtdpstore?
 * As there is no erase for panic case, we should ensure at least one zone
 * is writable. Otherwise, panic write will fail.
 * If zone is used, write operation will return -ENOMSG, which means that
 * pstore/blk will try one by one until gets an empty zone. So, it is not
 * needed to ensure the next zone is empty, but at least one.
 */
static int mtdpstore_security(struct mtdpstore_context *cxt, loff_t off)
{
	int ret = 0, i;
	struct mtd_info *mtd = cxt->mtd;
	u32 zonenum = (u32)div_u64(off, cxt->info.kmsg_size);
	u32 zonecnt = (u32)div_u64(cxt->mtd->size, cxt->info.kmsg_size);
	u32 blkcnt = (u32)div_u64(cxt->mtd->size, cxt->mtd->erasesize);
	u32 erasesize = cxt->mtd->erasesize;

	for (i = 0; i < zonecnt; i++) {
		u32 num = (zonenum + i) % zonecnt;

		/* found empty zone */
		if (!test_bit(num, cxt->usedmap))
			return 0;
	}

	/* If there is no any empty zone, we have no way but to do erase */
	while (blkcnt--) {
		div64_u64_rem(off + erasesize, cxt->mtd->size, (u64 *)&off);

		if (mtdpstore_block_isbad(cxt, off))
			continue;

		ret = mtdpstore_erase_do(cxt, off);
		if (!ret) {
			mtdpstore_block_mark_unused(cxt, off);
			break;
		}
	}

	if (ret)
		dev_err(&mtd->dev, "all blocks bad!\n");
	dev_dbg(&mtd->dev, "end security\n");
	return ret;
}

static ssize_t mtdpstore_write(const char *buf, size_t size, loff_t off)
{
	struct mtdpstore_context *cxt = &oops_cxt;
	struct mtd_info *mtd = cxt->mtd;
	size_t retlen;
	int ret;

	if (mtdpstore_block_isbad(cxt, off))
		return -ENOMSG;

	/* zone is used, please try next one */
	if (mtdpstore_is_used(cxt, off))
		return -ENOMSG;

	dev_dbg(&mtd->dev, "try to write off 0x%llx size %zu\n", off, size);
	ret = mtd_write(cxt->mtd, off, size, &retlen, (u_char *)buf);
	if (ret < 0 || retlen != size) {
		dev_err(&mtd->dev, "write failure at %lld (%zu of %zu written), err %d\n",
				off, retlen, size, ret);
		return -EIO;
	}
	mtdpstore_mark_used(cxt, off);

	mtdpstore_security(cxt, off);
	return retlen;
}

static inline bool mtdpstore_is_io_error(int ret)
{
	return ret < 0 && !mtd_is_bitflip(ret) && !mtd_is_eccerr(ret);
}

/*
 * All zones will be read as pstore/blk will read zone one by one when do
 * recover.
 */
static ssize_t mtdpstore_read(char *buf, size_t size, loff_t off)
{
	struct mtdpstore_context *cxt = &oops_cxt;
	struct mtd_info *mtd = cxt->mtd;
	size_t retlen, done;
	int ret;

	if (mtdpstore_block_isbad(cxt, off))
		return -ENOMSG;

	dev_dbg(&mtd->dev, "try to read off 0x%llx size %zu\n", off, size);
	for (done = 0, retlen = 0; done < size; done += retlen) {
		retlen = 0;

		ret = mtd_read(cxt->mtd, off + done, size - done, &retlen,
				(u_char *)buf + done);
		if (mtdpstore_is_io_error(ret)) {
			dev_err(&mtd->dev, "read failure at %lld (%zu of %zu read), err %d\n",
					off + done, retlen, size - done, ret);
			/* the zone may be broken, try next one */
			return -ENOMSG;
		}

		/*
		 * ECC error. The impact on log data is so small. Maybe we can
		 * still read it and try to understand. So mtdpstore just hands
		 * over what it gets and user can judge whether the data is
		 * valid or not.
		 */
		if (mtd_is_eccerr(ret)) {
			dev_err(&mtd->dev, "ecc error at %lld (%zu of %zu read), err %d\n",
					off + done, retlen, size - done, ret);
			/* driver may not set retlen when ecc error */
			retlen = retlen == 0 ? size - done : retlen;
		}
	}

	if (mtdpstore_is_empty(cxt, buf, size))
		mtdpstore_mark_unused(cxt, off);
	else
		mtdpstore_mark_used(cxt, off);

	mtdpstore_security(cxt, off);
	return retlen;
}

static ssize_t mtdpstore_panic_write(const char *buf, size_t size, loff_t off)
{
	struct mtdpstore_context *cxt = &oops_cxt;
	struct mtd_info *mtd = cxt->mtd;
	size_t retlen;
	int ret;

	if (mtdpstore_panic_block_isbad(cxt, off))
		return -ENOMSG;

	/* zone is used, please try next one */
	if (mtdpstore_is_used(cxt, off))
		return -ENOMSG;

	ret = mtd_panic_write(cxt->mtd, off, size, &retlen, (u_char *)buf);
	if (ret < 0 || size != retlen) {
		dev_err(&mtd->dev, "panic write failure at %lld (%zu of %zu read), err %d\n",
				off, retlen, size, ret);
		return -EIO;
	}
	mtdpstore_mark_used(cxt, off);

	return retlen;
}

static void mtdpstore_notify_add(struct mtd_info *mtd)
{
	int ret;
	struct mtdpstore_context *cxt = &oops_cxt;
	struct pstore_blk_config *info = &cxt->info;
	unsigned long longcnt;

	if (!strcmp(mtd->name, info->device))
		cxt->index = mtd->index;

	if (mtd->index != cxt->index || cxt->index < 0)
		return;

	dev_dbg(&mtd->dev, "found matching MTD device %s\n", mtd->name);

	if (mtd->size < info->kmsg_size * 2) {
		dev_err(&mtd->dev, "MTD partition %d not big enough\n",
				mtd->index);
		return;
	}
	/*
	 * kmsg_size must be aligned to 4096 Bytes, which is limited by
	 * psblk. The default value of kmsg_size is 64KB. If kmsg_size
	 * is larger than erasesize, some errors will occur since mtdpsotre
	 * is designed on it.
	 */
	if (mtd->erasesize < info->kmsg_size) {
		dev_err(&mtd->dev, "eraseblock size of MTD partition %d too small\n",
				mtd->index);
		return;
	}
	if (unlikely(info->kmsg_size % mtd->writesize)) {
		dev_err(&mtd->dev, "record size %lu KB must align to write size %d KB\n",
				info->kmsg_size / 1024,
				mtd->writesize / 1024);
		return;
	}

	longcnt = BITS_TO_LONGS(div_u64(mtd->size, info->kmsg_size));
	cxt->rmmap = kcalloc(longcnt, sizeof(long), GFP_KERNEL);
	cxt->usedmap = kcalloc(longcnt, sizeof(long), GFP_KERNEL);

	longcnt = BITS_TO_LONGS(div_u64(mtd->size, mtd->erasesize));
	cxt->badmap = kcalloc(longcnt, sizeof(long), GFP_KERNEL);

	cxt->dev.total_size = mtd->size;
	/* just support dmesg right now */
	cxt->dev.flags = PSTORE_FLAGS_DMESG;
	cxt->dev.read = mtdpstore_read;
	cxt->dev.write = mtdpstore_write;
	cxt->dev.erase = mtdpstore_erase;
	cxt->dev.panic_write = mtdpstore_panic_write;

	ret = register_pstore_device(&cxt->dev);
	if (ret) {
		dev_err(&mtd->dev, "mtd%d register to psblk failed\n",
				mtd->index);
		return;
	}
	cxt->mtd = mtd;
	dev_info(&mtd->dev, "Attached to MTD device %d\n", mtd->index);
}

static int mtdpstore_flush_removed_do(struct mtdpstore_context *cxt,
		loff_t off, size_t size)
{
	struct mtd_info *mtd = cxt->mtd;
	u_char *buf;
	int ret;
	size_t retlen;
	struct erase_info erase;

	buf = kmalloc(mtd->erasesize, GFP_KERNEL);
	if (!buf)
		return -ENOMEM;

	/* 1st. read to cache */
	ret = mtd_read(mtd, off, mtd->erasesize, &retlen, buf);
	if (mtdpstore_is_io_error(ret))
		goto free;

	/* 2nd. erase block */
	erase.len = mtd->erasesize;
	erase.addr = off;
	ret = mtd_erase(mtd, &erase);
	if (ret)
		goto free;

	/* 3rd. write back */
	while (size) {
		unsigned int zonesize = cxt->info.kmsg_size;

		/* there is valid data on block, write back */
		if (mtdpstore_is_used(cxt, off)) {
			ret = mtd_write(mtd, off, zonesize, &retlen, buf);
			if (ret)
				dev_err(&mtd->dev, "write failure at %lld (%zu of %u written), err %d\n",
						off, retlen, zonesize, ret);
		}

		off += zonesize;
		size -= min_t(unsigned int, zonesize, size);
	}

free:
	kfree(buf);
	return ret;
}

/*
 * What does mtdpstore_flush_removed() do?
 * When user remove any log file on pstore filesystem, mtdpstore should do
 * something to ensure log file removed. If the whole block is no longer used,
 * it's nice to erase the block. However if the block still contains valid log,
 * what mtdpstore can do is to erase and write the valid log back.
 */
static int mtdpstore_flush_removed(struct mtdpstore_context *cxt)
{
	struct mtd_info *mtd = cxt->mtd;
	int ret;
	loff_t off;
	u32 blkcnt = (u32)div_u64(mtd->size, mtd->erasesize);

	for (off = 0; blkcnt > 0; blkcnt--, off += mtd->erasesize) {
		ret = mtdpstore_block_isbad(cxt, off);
		if (ret)
			continue;

		ret = mtdpstore_block_is_removed(cxt, off);
		if (!ret)
			continue;

		ret = mtdpstore_flush_removed_do(cxt, off, mtd->erasesize);
		if (ret)
			return ret;
	}
	return 0;
}

static void mtdpstore_notify_remove(struct mtd_info *mtd)
{
	struct mtdpstore_context *cxt = &oops_cxt;

	if (mtd->index != cxt->index || cxt->index < 0)
		return;

	mtdpstore_flush_removed(cxt);

	unregister_pstore_device(&cxt->dev);
	kfree(cxt->badmap);
	kfree(cxt->usedmap);
	kfree(cxt->rmmap);
	cxt->mtd = NULL;
	cxt->index = -1;
}

static struct mtd_notifier mtdpstore_notifier = {
	.add	= mtdpstore_notify_add,
	.remove	= mtdpstore_notify_remove,
};

static int __init mtdpstore_init(void)
{
	int ret;
	struct mtdpstore_context *cxt = &oops_cxt;
	struct pstore_blk_config *info = &cxt->info;

	ret = pstore_blk_get_config(info);
	if (unlikely(ret))
		return ret;

	if (strlen(info->device) == 0) {
		pr_err("mtd device must be supplied (device name is empty)\n");
		return -EINVAL;
	}
	if (!info->kmsg_size) {
		pr_err("no backend enabled (kmsg_size is 0)\n");
		return -EINVAL;
	}

	/* Setup the MTD device to use */
	ret = kstrtoint((char *)info->device, 0, &cxt->index);
	if (ret)
		cxt->index = -1;

	register_mtd_user(&mtdpstore_notifier);
	return 0;
}
module_init(mtdpstore_init);

static void __exit mtdpstore_exit(void)
{
	unregister_mtd_user(&mtdpstore_notifier);
}
module_exit(mtdpstore_exit);

MODULE_LICENSE("GPL");
MODULE_AUTHOR("WeiXiong Liao <liaoweixiong@allwinnertech.com>");
MODULE_DESCRIPTION("MTD backend for pstore/blk");